20.500.12556/DKUM-67439 Preprečevanje prekomernega prileganja pri učenju večplastnih nevronskih mrež Overfitting prevention in training of multilayer neural networks Diplomsko delo obravnava tematiko strojnega učenja s pomočjo uporabe umetnih nevron- skih mrež. Te so po svojih sposobnostih in načinu delovanja zelo podobne delovanju človeških možganov. Imajo sposobnost akumuliranja znanja s tako imenovanim postop- kom ”učenja”, hkrati pa so sposobne to znanje tudi shranjevati. Pravilnost delovanja mrež se s postopkom učenja, ki se ponavlja iterativno, povečuje. Ena izmed glavnih težav pri učenju nevronskih mrež je pojav prekomernega prileganja, ki se kaže v tem, da mreža ne posplošuje dobro iz učne na testno množico vzorcev. Za preprečevanje tega pojava je bilo razvitih več tehnik, katerih uporaba, učinkovitost in primerjava je predmet pričujočega diplomskega dela. This thesis deals with the subject of machine learning by using artificial neural networks. They are very similar to the human brain in their abilities and way of functioning. They have the capacity to accumulate knowledge through the so-called “learning” process, but they are also able to store this knowledge. The accuracy of artificial neural networks is increased in the process of learning, which is repeated iteratively. One of the main problems in this process is the emergence of overfitting. This is because the network does not generalize well from the learning to the test set. To prevent this phenomenon several different techniques have been developed, the application and effectiveness of which have been analyzed and compared in the present thesis. Umetna nevronska mreža Vzvratno razširjanje Prekomerno prileganje Regularizacija Artificial neural network Backpropagation Overfitting Regularization true true false J. Henčič Slovenski jezik Angleški jezik Diplomsko delo/naloga 2017-08-17 19:35:17 2017-10-06 14:36:42 2022-08-01 13:58:51 2019-07-11 16:20:26 2017 0 [Maribor 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.85.032.26(043.2) 20869142 URN:SI:UM:DK:BLNIGGWX UN_Hencic_Jan_2017.pdf UN_Hencic_Jan_2017.pdf 1 387BC0D510BF2B3F4AEDCB2EBCBDBCD3 59bbdf2d2f96757f89d119948058c39981e292bb834e18f55fa9e2fdf9656a04 8695d274-7c0e-11eb-bb7a-00155d0001ca 20.500.12556/dkum/38e21d8a-9384-4ef3-90bf-0a63432abf68 https://dk.um.si/Dokument.php?lang=slv&id=115483 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0